commit 13db0bf3eb2e53ff771ac1c06a4dbd6b98352e0e Author: ModelHub XC Date: Sun Sep 13 00:22:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: ThomasBaruzier/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..58bf58b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,64 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +imatrix.dat filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-F16.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-F16.gguf b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-F16.gguf new file mode 100644 index 0000000..808dec2 --- /dev/null +++ b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71184082a0483beb5bbc39a42ca23a8ef8ec61f5a1f9cc4dc9b1dfec45df12bc +size 3561205920 diff --git a/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ1_M.gguf b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ1_M.gguf new file mode 100644 index 0000000..e8f67a6 --- /dev/null +++ b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6f8e771b9677f654813845e0b921880811c412eb351b020d21da3a5612bb08c +size 541239776 diff --git a/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ1_S.gguf b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ1_S.gguf new file mode 100644 index 0000000..e928ac2 --- /dev/null +++ b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc601a15f36feace65336da5cc78306bf4fc318342b55224b1d5171cd8c4dbc8 +size 513306080 diff --git a/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ2_M.gguf b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ2_M.gguf new file mode 100644 index 0000000..9e0e72f --- /dev/null +++ b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09784314d3d7d312e7752ac0288bd514fd037b551a10b5549ef9d818bc9b0d1b +size 701555168 diff --git a/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ2_S.gguf b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ2_S.gguf new file mode 100644 index 0000000..9db40bf --- /dev/null +++ b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0151aa669c24c37d01a165c77721251b1a83e7f5b0f3776dd195c525bdf13785 +size 664310240 diff --git a/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ2_XS.gguf b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ2_XS.gguf new file mode 100644 index 0000000..bffd633 --- /dev/null +++ b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da628062de25c4cfaaec8594cc759eede1456156a893aa3717a9a238b17142c2 +size 627105248 diff --git a/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ2_XXS.gguf b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ2_XXS.gguf new file mode 100644 index 0000000..6406226 --- /dev/null +++ b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acad027d9d81f0fa56861525a5fefa8b0d114663f798537a85a0b760df3ebd0f +size 587795936 diff --git a/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ3_M.gguf b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ3_M.gguf new file mode 100644 index 0000000..4a0ab96 --- /dev/null +++ b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f349d075a9b933e2c7ad5a90432c509b00a58acc2d58909b6f55e51479ca9e25 +size 877190624 diff --git a/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ3_S.gguf b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ3_S.gguf new file mode 100644 index 0000000..998e6b7 --- /dev/null +++ b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5dacf065288e7cc0bb11a9b694addf5cf3f35d66ce6d13590cade2c634e1674 +size 862933472 diff --git a/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ3_XS.gguf b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ3_XS.gguf new file mode 100644 index 0000000..137b95d --- /dev/null +++ b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cb6e61850c45d4beb0cf6013efed7f2aaf6fba14746d44d4ac316b5d52f085e +size 832225760 diff --git a/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ3_XXS.gguf b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ3_XXS.gguf new file mode 100644 index 0000000..b0eb3d3 --- /dev/null +++ b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c33c51963d031d22427cc7b2a391a3245c4c23103de663aa5c8921d088d94192 +size 769292768 diff --git a/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ4_NL.gguf b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ4_NL.gguf new file mode 100644 index 0000000..dbd93b7 --- /dev/null +++ b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f98a9c5ceaa4be44fc03a2be6af7886a0505e0bb5fa471f4a20d13b75e4f5e3 +size 1067878880 diff --git a/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ4_XS.gguf b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ4_XS.gguf new file mode 100644 index 0000000..dd360bc --- /dev/null +++ b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:facb1b6c1971d2a603a9dbdf01cdf92ee590a5c70e6dbdd022b96c8185a90792 +size 1019980256 diff --git a/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q2_K.gguf b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q2_K.gguf new file mode 100644 index 0000000..63e6d02 --- /dev/null +++ b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d82a1f01a51721baa27adf5577e0b9998df502f7deafefcdf64ad5f8271bdd7 +size 753109472 diff --git a/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q2_K_S.gguf b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q2_K_S.gguf new file mode 100644 index 0000000..d5196a9 --- /dev/null +++ b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:847bc5aed6748f36977daf171dbad0fd672f5de36471a8957bb63bf47fa1b4a5 +size 716939744 diff --git a/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q3_K_L.gguf b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q3_K_L.gguf new file mode 100644 index 0000000..57d57d2 --- /dev/null +++ b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4698ae1e173211ece8791ec578469c57e726a96b705b21bd2c3c5c172fe66d13 +size 980689376 diff --git a/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q3_K_M.gguf b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q3_K_M.gguf new file mode 100644 index 0000000..1d4a6d7 --- /dev/null +++ b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc0327c6a89b6fee93680f2d8597c216899a73b88f620b10c7b2ce0ce5ffac38 +size 924705248 diff --git a/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q3_K_S.gguf b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q3_K_S.gguf new file mode 100644 index 0000000..80c1e89 --- /dev/null +++ b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:885c7b1642ddf657b1680c1bc1830285e2301f48988c256ec837e911252ef1a5 +size 861471200 diff --git a/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q4_0.gguf b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q4_0.gguf new file mode 100644 index 0000000..a94047f --- /dev/null +++ b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:580f7cecd45b5ee8676d0201ee1aacc66d660c56b502ab10b73db2f5c4c26f1f +size 1069083104 diff --git a/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q4_1.gguf b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q4_1.gguf new file mode 100644 index 0000000..3f0f00e --- /dev/null +++ b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f9beca21b8fd0ad5bccd51240434157684686a8d6d18839118ea6df46e94216 +size 1162988000 diff --git a/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q4_K_M.gguf b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q4_K_M.gguf new file mode 100644 index 0000000..ea28588 --- /dev/null +++ b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6a9f0ca7c47ea633c8fd2f612f45f0d9812dee6567a6ad2efe64a0ab67d42c7 +size 1117596128 diff --git a/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q4_K_S.gguf b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q4_K_S.gguf new file mode 100644 index 0000000..a41fd00 --- /dev/null +++ b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40d466177f25c52c15ab62e4cb08f7784f050ea38f453ec6807f7e439affb677 +size 1071860192 diff --git a/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q5_0.gguf b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q5_0.gguf new file mode 100644 index 0000000..8aa15b7 --- /dev/null +++ b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0070372b5dd94a495fc99175d144dc65a0ff833d7b077d0fedceaaaec5fdab88 +size 1262053856 diff --git a/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q5_1.gguf b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q5_1.gguf new file mode 100644 index 0000000..358ecfc --- /dev/null +++ b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1747fbc98b6ea2514c3e6a6d0511f7646488f03107f190f67aa1a81140391746 +size 1355958752 diff --git a/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q5_K_M.gguf b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q5_K_M.gguf new file mode 100644 index 0000000..338197a --- /dev/null +++ b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:873b432c20d29aa5ce36a455839185cd0b1b12a9a322e239910e44bdb16f8fb5 +size 1285794272 diff --git a/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q5_K_S.gguf b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q5_K_S.gguf new file mode 100644 index 0000000..7fc5dcc --- /dev/null +++ b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ecc75203df8b5358962d4bda9409ebb86a15b8d43f1bdffc26b2420914e8e45 +size 1259473376 diff --git a/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q6_K.gguf b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q6_K.gguf new file mode 100644 index 0000000..43e5e44 --- /dev/null +++ b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6aadc2ab4862d70cc68cee143432212e83ffeee631da0e367960586d87efb9ee +size 1464504800 diff --git a/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q8_0.gguf b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q8_0.gguf new file mode 100644 index 0000000..2ee2c07 --- /dev/null +++ b/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56719155b23523520976eb47a2203198498569dcd7e4c3c8a103843819bb9097 +size 1894953440 diff --git a/README.md b/README.md new file mode 100644 index 0000000..89529f2 --- /dev/null +++ b/README.md @@ -0,0 +1,124 @@ +--- +license: mit +train: false +inference: true +pipeline_tag: text-generation +base_model: +- deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B +--- + +

+ +# Llama.cpp imatrix quantizations of [mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1](https://huggingface.co/mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1) + +Using llama.cpp commit [3ad5451](https://github.com/ggerganov/llama.cpp/commit/3ad5451) for quantization. + +All quants were made using the imatrix option and Bartowski's [calibration file](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8). + +
+ +# Perplexity table (the lower the better) + +| Quant | Size (MB) | PPL | Size (%) | Accuracy (%) | PPL error rate | +| ------------------------------------------------------------------------------------------------------------------------------------------------------ | --------- | ------- | -------- | ------------ | -------------- | +| [IQ1_S](https://huggingface.co/ThomasBaruzier/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ1_S.gguf) | 489 | 88.4250 | 14.40 | 23.35 | 1.76 | +| [IQ1_M](https://huggingface.co/ThomasBaruzier/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ1_M.gguf) | 516 | 53.8278 | 15.19 | 38.35 | 1.03 | +| [IQ2_XXS](https://huggingface.co/ThomasBaruzier/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ2_XXS.gguf) | 560 | 45.5693 | 16.49 | 45.31 | 0.93 | +| [IQ2_XS](https://huggingface.co/ThomasBaruzier/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ2_XS.gguf) | 598 | 32.6813 | 17.61 | 63.17 | 0.62 | +| [IQ2_S](https://huggingface.co/ThomasBaruzier/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ2_S.gguf) | 633 | 28.5477 | 18.64 | 72.32 | 0.54 | +| [IQ2_M](https://huggingface.co/ThomasBaruzier/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ2_M.gguf) | 669 | 31.8272 | 19.70 | 64.87 | 0.63 | +| [Q2_K_S](https://huggingface.co/ThomasBaruzier/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q2_K_S.gguf) | 683 | 28.7707 | 20.11 | 71.76 | 0.54 | +| [Q2_K](https://huggingface.co/ThomasBaruzier/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q2_K.gguf) | 718 | 27.6342 | 21.14 | 74.71 | 0.51 | +| [IQ3_XXS](https://huggingface.co/ThomasBaruzier/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ3_XXS.gguf) | 733 | 23.5511 | 21.58 | 87.66 | 0.44 | +| [IQ3_XS](https://huggingface.co/ThomasBaruzier/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ3_XS.gguf) | 793 | 22.9887 | 23.35 | 89.81 | 0.42 | +| [Q3_K_S](https://huggingface.co/ThomasBaruzier/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q3_K_S.gguf) | 821 | 28.0462 | 24.17 | 73.61 | 0.53 | +| [IQ3_S](https://huggingface.co/ThomasBaruzier/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ3_S.gguf) | 822 | 22.9268 | 24.20 | 90.05 | 0.42 | +| [IQ3_M](https://huggingface.co/ThomasBaruzier/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ3_M.gguf) | 836 | 22.3167 | 24.62 | 92.51 | 0.41 | +| [Q3_K_M](https://huggingface.co/ThomasBaruzier/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q3_K_M.gguf) | 881 | 22.5727 | 25.94 | 91.46 | 0.41 | +| [Q3_K_L](https://huggingface.co/ThomasBaruzier/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q3_K_L.gguf) | 935 | 22.3758 | 27.53 | 92.27 | 0.41 | +| [IQ4_XS](https://huggingface.co/ThomasBaruzier/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ4_XS.gguf) | 972 | 21.3273 | 28.62 | 96.80 | 0.38 | +| [IQ4_NL](https://huggingface.co/ThomasBaruzier/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-IQ4_NL.gguf) | 1018 | 21.3234 | 29.98 | 96.82 | 0.38 | +| [Q4_0](https://huggingface.co/ThomasBaruzier/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q4_0.gguf) | 1019 | 22.5210 | 30.00 | 91.67 | 0.41 | +| [Q4_K_S](https://huggingface.co/ThomasBaruzier/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q4_K_S.gguf) | 1022 | 21.1717 | 30.09 | 97.51 | 0.38 | +| [Q4_K_M](https://huggingface.co/ThomasBaruzier/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q4_K_M.gguf) | 1065 | 21.0532 | 31.36 | 98.06 | 0.38 | +| [Q4_1](https://huggingface.co/ThomasBaruzier/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q4_1.gguf) | 1109 | 21.1492 | 32.66 | 97.62 | 0.38 | +| [Q5_K_S](https://huggingface.co/ThomasBaruzier/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q5_K_S.gguf) | 1201 | 20.7883 | 35.37 | 99.31 | 0.37 | +| [Q5_0](https://huggingface.co/ThomasBaruzier/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q5_0.gguf) | 1203 | 20.8643 | 35.42 | 98.95 | 0.37 | +| [Q5_K_M](https://huggingface.co/ThomasBaruzier/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q5_K_M.gguf) | 1226 | 20.7488 | 36.10 | 99.50 | 0.37 | +| [Q5_1](https://huggingface.co/ThomasBaruzier/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q5_1.gguf) | 1293 | 20.7773 | 38.07 | 99.37 | 0.37 | +| [Q6_K](https://huggingface.co/ThomasBaruzier/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q6_K.gguf) | 1396 | 20.6994 | 41.11 | 99.74 | 0.37 | +| [Q8_0](https://huggingface.co/ThomasBaruzier/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q8_0.gguf) | 1807 | 20.6659 | 53.21 | 99.90 | 0.37 | +| [F16](https://huggingface.co/ThomasBaruzier/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-F16.gguf) | 3396 | 20.6457 | 100 | 100 | 0.37 | + +
+ +This is a version of the DeepSeek-R1-Distill-Qwen-1.5B model re-distilled for better performance. + +## Performance + +| Models | DeepSeek-R1-Distill-Qwen-1.5B | DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1 | +|:-------------------:|:--------:|:----------------:| +| ARC (25-shot) | 40.96 | 41.55 | +| HellaSwag (10-shot)| 44 | 45.88 | +| MMLU (5-shot) | 39.27 | 41.82 | +| TruthfulQA-MC2 | 45.17 | 46.63 | +| Winogrande (5-shot)| 55.49 | 57.7 | +| GSM8K (5-shot) | 69.9 | 74.3 | +| Average | 49.13 | 51.31 | + +| Models | DeepSeek-R1-Distill-Qwen-1.5B | DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1 | +|:-------------------:|:--------:|:----------------:| +| GPQA (0-shot) | 26.96 | 26.99 | +| MMLU PRO (5-shot) | 16.74 | 19.86 | +| MUSR (0-shot) | 35.93 | 36.6 | +| BBH (3-shot) | 35.12 | 37.23 | +| IfEval (0-shot) | 24.94 | 27.22 | + +## Usage +```Python +import torch +from transformers import AutoModelForCausalLM, AutoTokenizer +compute_dtype = torch.bfloat16 +device = 'cuda' +model_id = "mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1" + +model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=compute_dtype, attn_implementation="sdpa", device_map=device) +tokenizer = AutoTokenizer.from_pretrained(model_id) + +prompt = "What is 1.5+102.2?" +chat = tokenizer.apply_chat_template([{"role":"user", "content":prompt}], tokenize=True, add_generation_prompt=True, return_tensors="pt") +outputs = model.generate(chat.to(device), max_new_tokens=1024, do_sample=True) +print(tokenizer.decode(outputs[0])) +``` + +Output: +``` +<｜begin▁of▁sentence｜><｜User｜>What is 1.5+102.2?<｜Assistant｜> +First, I identify the numbers involved in the addition: 1.5 and 102.2. + +Next, I add the whole numbers: 1 + 102 equals 103. + +Then, I add the decimal parts: 0.5 + 0.2 equals 0.7. + +Finally, I combine the results: 103 + 0.7 equals 103.7. + + +To solve the addition \(1.5 + 102.2\), follow these steps: + +1. **Add the whole numbers:** + \[ + 1 + 102 = 103 + \] + +2. **Add the decimal parts:** + \[ + 0.5 + 0.2 = 0.7 + \] + +3. **Combine the results:** + \[ + 103 + 0.7 = 103.7 + \] + +So, the final answer is \(\boxed{103.7}\).<｜end▁of▁sentence｜> +``` \ No newline at end of file diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..fd5ac31 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ac3019c63463c07e13d3c2be68be38fd4cd31930809934a54fac6398d734d69 +size 2042232 diff --git a/perplexity.md b/perplexity.md new file mode 100644 index 0000000..bd202f1 --- /dev/null +++ b/perplexity.md @@ -0,0 +1,30 @@ +| Quant | Size (MB) | PPL | Size (%) | Accuracy (%) | PPL error rate | +| ------ | --------- | ------- | -------- | ------------ | -------------- | +| IQ1_S | 489 | 88.4250 | 14.40 | 23.35 | 1.76 | +| IQ1_M | 516 | 53.8278 | 15.19 | 38.35 | 1.03 | +| IQ2_XXS | 560 | 45.5693 | 16.49 | 45.31 | 0.93 | +| IQ2_XS | 598 | 32.6813 | 17.61 | 63.17 | 0.62 | +| IQ2_S | 633 | 28.5477 | 18.64 | 72.32 | 0.54 | +| IQ2_M | 669 | 31.8272 | 19.70 | 64.87 | 0.63 | +| Q2_K_S | 683 | 28.7707 | 20.11 | 71.76 | 0.54 | +| Q2_K | 718 | 27.6342 | 21.14 | 74.71 | 0.51 | +| IQ3_XXS | 733 | 23.5511 | 21.58 | 87.66 | 0.44 | +| IQ3_XS | 793 | 22.9887 | 23.35 | 89.81 | 0.42 | +| Q3_K_S | 821 | 28.0462 | 24.17 | 73.61 | 0.53 | +| IQ3_S | 822 | 22.9268 | 24.20 | 90.05 | 0.42 | +| IQ3_M | 836 | 22.3167 | 24.62 | 92.51 | 0.41 | +| Q3_K_M | 881 | 22.5727 | 25.94 | 91.46 | 0.41 | +| Q3_K_L | 935 | 22.3758 | 27.53 | 92.27 | 0.41 | +| IQ4_XS | 972 | 21.3273 | 28.62 | 96.80 | 0.38 | +| IQ4_NL | 1018 | 21.3234 | 29.98 | 96.82 | 0.38 | +| Q4_0 | 1019 | 22.5210 | 30.00 | 91.67 | 0.41 | +| Q4_K_S | 1022 | 21.1717 | 30.09 | 97.51 | 0.38 | +| Q4_K_M | 1065 | 21.0532 | 31.36 | 98.06 | 0.38 | +| Q4_1 | 1109 | 21.1492 | 32.66 | 97.62 | 0.38 | +| Q5_K_S | 1201 | 20.7883 | 35.37 | 99.31 | 0.37 | +| Q5_0 | 1203 | 20.8643 | 35.42 | 98.95 | 0.37 | +| Q5_K_M | 1226 | 20.7488 | 36.10 | 99.50 | 0.37 | +| Q5_1 | 1293 | 20.7773 | 38.07 | 99.37 | 0.37 | +| Q6_K | 1396 | 20.6994 | 41.11 | 99.74 | 0.37 | +| Q8_0 | 1807 | 20.6659 | 53.21 | 99.90 | 0.37 | +| F16 | 3396 | 20.6457 | 100 | 100 | 0.37 |